The surveillance of the maritime traffic is a major issue for defense contexts (e.g., surveillance of specific zones, borders,...) as well as security and monitoring contexts (e.g., monitoring of the maritime traffic, of fisheries activities). Spaceborn technologies, especially satellite ship tracking from AIS messages (Automatic Identification System) and high-resolution imaging of sea surface, open new avenues to address such monitoring and surveillance objectives. However, operational systems cannot currently fully process these satellite-derived data streams. For instance, the CRM (Centre de Renseignement de la Marine) evaluates that less than 20% of the overall AIS data (about a few tens of millions of AIS messages daily) are actually analysed for abnormal behaviour detection. Besides, the free access to Sentinel earth observation data streams (high-resolution SAR and optical imaging, up to a few Tb daily) offers novel opportunities for the analysis and detection of ship behaviours, including AIS-Sentinel data synergies. In this context, SESAME initiative aims at developing new big-data-oriented approaches to deliver novel solutions for the management, analysis and visualization of multi-source satellite data streams. Targeted at the automatic generation and documenting of early warnings (both in real-time and re- analysis modes), the key scientific and technological challenges cover the development of hardware and software platforms adapted to the volume and the features of the data streams to be processed along with the design of novel models and algorithms for AIS-Sentinel synergies and the automatic detection and recognition of abnormal behaviours. The originality of the project lies in a big-data approach to jointly address these challenges based on the complementarity of the scientific expertise gathered in the consortium: big-data platforms, mining strategies for time series, modeling and analysis of tracking data, Sat-AIS signal analysis, high-resolution satellite imaging. It involves four main scientific and technical tasks: Hardware and software platforms for the management, processing and visualization of multi-source satellite data streams for maritime traffic surveillance (Task 1), Analysis, modeling and detection of marine vessel behaviours from AIS data streams (Task 2), AIS-Sentinel data synergies for maritime traffic surveillance (Task 3), Visualization and mining of large-scale augmented marine vessel tracking databases (Task 4). A fifth task embeds the implementation of the proposed solutions for dual case-studies representative of the scientific and technical objectives targeted by the project. For the specification of the case-studies as well as the critical assessment phase at the end of the project, we will invite additional external thematic expertise to the consortium (e.g., EMSA, European Maritime Safety Agency). SESAME initiative, from its consortium formed by three academic members (Lab-STICC/TOMS, IRISA/MYRIADS, IRISA/OBELIX) and one industrial member (CLS), will implement an applied research program with a TRL-4 target. The expected impacts of the project include both dissemination actions to the scientific community, including a maritime traffic surveillance benchmark suite, and technological transfers to CLS with respect to future national and international calls on operational systems and services for maritime traffic surveillance and high-resolution environment monitoring.

Partners: IMT Atlantique/Lab-STICC, INRIA Rennes/Myriads, IRISA/Obelix, CLS

Funding body: ANR/DGA

Role in the project: Principal Investigator